Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1752 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1444. Min Act: -0.0000

Data Index: 665359 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1213. Min Act: -0.0000

Data Index: 69629 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1284604 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1173. Min Act: -0.0000

Data Index: 102360 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1104. Min Act: -0.0000

Data Index: 609169 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1116. Min Act: -0.0000

Data Index: 917973 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1075. Min Act: -0.0000

Data Index: 181791 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1042. Min Act: -0.0000

Data Index: 915347 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1041. Min Act: -0.0000

Data Index: 745508 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1011. Min Act: -0.0000

Data Index: 645663 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1091363 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0985. Min Act: -0.0000

Data Index: 630617 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0939. Min Act: -0.0000

Data Index: 535484 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1275694 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1572311 (Python Code)

Max Activating Token Index: 186

Text #15

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1126194 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1266910 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0938. Min Act: -0.0000

Data Index: 50274 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0906. Min Act: -0.0000

Data Index: 741022 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1117914 (C4 (Web Text))

Max Activating Token Index: 818